Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting elements within equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    math and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Olvid
    -0.44
     gustó
    -0.29
    、
    -0.28
     supuestamente
    -0.28
     anunci
    -0.27
     originalmente
    -0.27
     образом
    -0.26
     değiştir
    -0.26
     znám
    -0.26
     ника
    -0.26
    POSITIVE LOGITS
     zwiſchen
    0.97
     ſans
    0.94
    ſſung
    0.93
    niſſe
    0.92
    ロウィン
    0.92
    ſicht
    0.91
    <unused28>
    0.91
    <unused51>
    0.91
    [@BOS@]
    0.91
    <pad>
    0.91
    Act Density 0.113%

    No Known Activations